© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1141
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal evidence and its relationship to personal claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "any"

    np_acts-logits-general · gemini-2.0-flash

    any

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     некоторые
    -0.44
     certains
    -0.42
     sometimes
    -0.41
     certaines
    -0.40
     algunos
    -0.40
    ScopeManager
    -0.40
     кое
    -0.39
     بعض
    -0.38
    expandindo
    -0.38
     algunas
    -0.38
    POSITIVE LOGITS
     any
    0.95
     ANY
    0.90
     anywhere
    0.87
     whatsoever
    0.87
     quelconque
    0.81
    任何
    0.81
     apapun
    0.78
    有任何
    0.77
     anything
    0.77
     quelcon
    0.77
    Activations Density 0.824%

    No Known Activations